Abstract
As a representative deep learning model, Convolutional Neural Networks (CNNs) can provide good features to represent the objects in image, and has made a great achievement in image classification and object detection. However, CNNs requires resizing the input images to a fixed size, which may affect the performance of the model due to information loss and distortion. To overcome the limitation, we replace the last pooling layer with topic model-LDA (Latent Dirichlet Allocation) to get a fixed-size output without resizing the input images, and we call it Topic Network. With Topic Network, the input images can be images of an arbitrary size and ratio without resizing, but the output is a k-dimension vector which represents the distribution of topics in image (k is the number of topics). Topic Network performs well in image classification task on Caltech101 and VOC2007 datasets.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part III. LNCS, vol. 8691, pp. 346–361. Springer, Heidelberg (2014)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part I. LNCS, vol. 8689, pp. 818–833. Springer, Heidelberg (2014)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 580–587. IEEE (2014)
Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. The Journal of Machine Learning Research 3, 993–1022 (2003)
Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. Computer Vision and Image Understanding 106, 59–70 (2007)
Everingham, M., Van Gool, L., Williams, C., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2007 (VOC 2007)
Griffiths, T.L., Steyvers, M.: Finding scientific topics. Proceedings of the National academy of Sciences of the United States of America 101, 5228–5235 (2004)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 60, 91–110 (2004)
Fei-Fei, L., Perona, P.: A bayesian hierarchical model for learning natural scene categories. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005, pp. 524–531. IEEE (2005)
Li, L.-J., Socher, R., Fei-Fei, L.: Towards total scene understanding: classification, annotation and segmentation in an automatic framework. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 2036–2043. IEEE (2009)
Cao, L., Fei-Fei, L.: Spatially coherent latent topic model for concurrent segmentation and classification of objects and scenes. In: IEEE 11th International Conference on Computer Vision, ICCV 2007, pp. 1–8. IEEE (2007)
Zhao, B., Fei-Fei, L., Xing, E.P.: Image segmentation with topic random field. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part V. LNCS, vol. 6315, pp. 785–798. Springer, Heidelberg (2010)
Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2169–2178. IEEE (2006)
Fan, R.-E., Chang, K.-W., Hsieh, C.-J., Wang, X.-R., Lin, C.-J.: LIBLINEAR: A library for large linear classification. The Journal of Machine Learning Research 9, 1871–1874 (2008)
Wang, J., Yang, J., Yu, K., Lv, F., Huang, T., Gong, Y.: Locality-constrained linear coding for image classification. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3360–3367. IEEE (2010)
Perronnin, F., Sánchez, J., Mensink, T.: Improving the fisher kernel for large-scale image classification. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 143–156. Springer, Heidelberg (2010)
Chatfield, K., Lempitsky, V.S., Vedaldi, A., Zisserman, A.: The devil is in the details: an evaluation of recent feature encoding methods. In: BMVC, p. 8 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Pan, Z., Liu, Y., Liu, G., Guo, M., Li, Y. (2015). Topic Network: Topic Model with Deep Learning for Image Classification. In: Zhang, S., Wirsing, M., Zhang, Z. (eds) Knowledge Science, Engineering and Management. KSEM 2015. Lecture Notes in Computer Science(), vol 9403. Springer, Cham. https://doi.org/10.1007/978-3-319-25159-2_47
Download citation
DOI: https://doi.org/10.1007/978-3-319-25159-2_47
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-25158-5
Online ISBN: 978-3-319-25159-2
eBook Packages: Computer ScienceComputer Science (R0)